Cyber Resilience

CVE-2025-7021

MediumPublic PoC

Published: 10 July 2025

Published
10 July 2025
Modified
24 July 2025
KEV Added
—
Patch
—
CVSS Score v4 6.9 CVSS:4.0/AV:N/AC:H/AT:N/PR:L/UI:P/VC:H/VI:N/VA:N/SC:H/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X
EPSS Score 0.0016 36.5th percentile
Risk Priority 14 60% EPSS · 20% KEV · 20% CVSS

Summary

CVE-2025-7021 is a medium-severity User Interface (UI) Misrepresentation of Critical Information (CWE-451) vulnerability in Openai Operator. Its CVSS base score is 6.9 (Medium).

Operationally, exploitation aligns with the MITRE ATT&CK technique GUI Input Capture (T1056.002); ranked at the 36.5th percentile by exploit likelihood (below the median); it is not currently listed in the CISA KEV catalog; a public proof-of-concept is referenced.

This vulnerability is AI-related — categorised as Enterprise AI Assistants; in the Privacy and Disclosure risk domain.

EU & UK References

Vulnerability details

Fullscreen API Spoofing and UI Redressing in the handling of Fullscreen API and UI rendering in OpenAI Operator SaaS on Web allows a remote attacker to capture sensitive user input (e.g., login credentials, email addresses) via displaying a deceptive fullscreen…

more

interface with overlaid fake browser controls and a distracting element (like a cookie consent screen) to obscure fullscreen notifications, tricking the user into interacting with the malicious site.

CWE(s)
CWE-451NVD-CWE-Other

AI Security AnalysisAI

AI Category
Enterprise AI Assistants
Risk Domain
Privacy and Disclosure
OWASP Top 10 for LLMs 2025
None mapped
Classification Reason
Matched keywords: openai

Related Threats

MITRE ATT&CK Enterprise TechniquesAI

T1056.002 GUI Input Capture Collection
Adversaries may mimic common operating system GUI components to prompt users for credentials with a seemingly legitimate prompt.
attack.mitre.org →
T1189 Drive-by Compromise Initial Access
Adversaries may gain access to a system through a user visiting a website over the normal course of browsing.
attack.mitre.org →
Why these techniques?

Vulnerability enables GUI input capture (T1056.002) by spoofing Fullscreen API notifications and overlaying deceptive fake browser controls/iframes to trick interactions; facilitated via drive-by compromise (T1189) when the OpenAI Operator SaaS visits a malicious page.

Affected Assets

openai
operator
all versions

Mitigating Controls

No mitigating controls mapped yet. The per-CVE control annotator has not reached this CVE.

References